arXiv (OAI Expanded)
open access
FastE: Readout-Triggered Token Compression for LLM Embedding Inference
In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qwen3-Embedding and Qwen3-VL-Embedding. We find that removing prefix states is substantially more damaging in shallow layers than at greater depth, sh
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- There is No Theoretical Curse of Multilinguality For Embedding Space Structure#985214
- To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs#1109526
- ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World#187351
- Why Does Post-Training Quantization Work?#999407
- TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories#820699
Record · ID 1056376
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive